Feature Acceptance Review

    1

    Generate traceable acceptance matrices by mapping source code and test logs against feature requirements.

    $2.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Feature Acceptance Review

    Example session with this skill installed

    Review the implementation of the Password Validation feature in /src/auth.ts against the criteria in requirements.md. I have attached the Vitest output in logs.txt.

    • Read your context and instructions
    • Compiled the feature acceptance review

    I have analyzed the password validation logic against your requirements. The review identifies two demonstrated criteria, one unproven claim regarding special characters, and one blocking deviation in the length constraint logic.

    Feature Acceptance Matrix

    IDCriterionEvidence LocationStatusNotes
    REQ-01Must be at least 8 charsauth.ts:L12, logs.txt:T4ContradictedCode checks >= 10 but requirement states 8.
    REQ-02Must contain a numberauth.ts:L15, logs.txt:T5DemonstratedRegex /\d/ correctly implemented and tested.
    REQ-03Must contain special charauth.ts:L18Not DemonstratedLogic exists in code but no corresponding test in logs.txt.
    REQ-04No leading/trailing spacesauth.ts:L10, logs.txt:T6Demonstrated.trim() called before validation sequence.

    Blocking Deviations

    REQ-01 (Length Mismatch): The implementation enforces a minimum length of 10, which is stricter than the agreed 8. This will cause valid user passwords to be rejected.

    • Check: Update MIN_LENGTH constant in auth.ts to 8.

    Verification Checklist

    1. Regression: Run Vitest with a 8-character string to confirm it now passes.

    Missing Evidence: Add a unit test specifically targeting the special character regex (REQ-03) to move status to Demonstrated.
    3.

    Clarification: Confirm if "special character" includes spaces or only symbols, as the current regex excludes whitespace.

    Next steps

    • Update the length constant in src/auth.ts.
    • Add the missing test case for special characters to your test suite.
    • Re-run the review with the updated logs to close REQ-01 and REQ-03.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Verification of feature completion is often subjective, leading to missed requirements and shipping bugs. This skill formalizes the review process by mapping implementation and test evidence against explicit acceptance criteria to generate a traceable compliance matrix.

    What it does

    • Requirement extraction Identifies specific acceptance criteria from project agreements while flagging ambiguous or conflicting requirements.
    • Evidence mapping Links each criterion to specific source code, unit tests, or execution logs to prove implementation.
    • Gap analysis Identifies missing evidence, code contradictions, or unproven claims that could lead to production failure.
    • Traceability matrix Generates a structured report showing the relationship between criteria, evidence, and current status.
    • Deviation logging Documents specific gaps between requirements and implementation with suggested remediation steps.

    How it works

    1. Supply the feature requirements or acceptance criteria along with the relevant source code and test results.
    2. The agent extracts individual criteria IDs and maps them to the provided implementation files.
    3. It evaluates the evidence, distinguishing between source-level inspection and actual runtime test results.
    4. It generates an acceptance matrix using specific states: demonstrated, contradicted, not demonstrated, or needs clarification.
    5. You receive a final report detailing blocking deviations and a focused checklist for manual or regression testing.

    Frameworks & tools

    This skill is language-agnostic and works with any text-based requirements (Markdown, Jira exports) and source code. It relies on provided test evidence such as Jest, PyTest, or Vitest logs.

    Why this beats prompting it yourself

    Standard prompts often give a binary "looks good" or "passed" without granular evidence. This skill enforces a strict evidence-based mapping that distinguishes between code existence and runtime verification, preventing false positives.

    Use cases

    • Reviewing a Pull Request against a specific Jira ticket or User Story.
    • Auditing a feature before a QA hand-off to minimize back-and-forth.
    • Generating compliance documentation for regulated software environments.

    Known limitations

    Does not execute code, run tests, or access external networks. It requires user-supplied evidence and cannot verify runtime behavior that is not documented in the provided logs or source code.

    Requires user-supplied logs or test results to verify runtime behavior. Does not execute code or run test suites. Cannot verify UI/UX quality without explicit visual logs or source.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 10 days ago

    Permissions

    Read Files
    Write Files
    Listed10 days ago
    Updated8 days ago

    What's inside

    Frequently Asked Questions

    This skill solves the problem of 'subjective verification' by requiring direct evidence mapping—linking specific lines of code and test log outputs to each requirement to ensure nothing is missed before shipping.

    The skill is language-agnostic and works with any text-based requirement format (like Markdown or Jira exports) and standard test logs from frameworks like Jest, PyTest, or Vitest.

    No, for security and reliability, this skill does not execute code; it performs a deep analysis of the source code and execution logs you provide to generate the traceability matrix.

    You receive the core logic for the Feature Acceptance Review skill, a set of configuration templates for different requirement formats, and a guide on how to structure your test logs for optimal evidence mapping.

    Unlike a general prompt, this skill uses a structured multi-step evaluation process that categorizes findings into specific states like 'demonstrated,' 'contradicted,' or 'needs clarification,' preventing the vague 'looks good' responses typical of basic LLM queries.

    New in Testing & Debugging